SKILLEMALL.ai
GitHub ↗ RU Sign in

BC nis2

EU NIS2 Directive (Directive (EU) 2022/2555) compliance advisor for essential and important entities: entity classification, Art. 21 risk management measures, Art. 23 incident reporting timelines (24h/72h/1 month), Art. 20 governance obligations, supply chain security (Art. 21(2)(d); coordinated risk assessments Art. 22), gap assessments, policy drafting, ISO 27001 alignment, and penalty exposure analysis. Also covers Commission Implementing Regulation (EU) 2024/2690, the technical/methodological sub-requirements for Art. 21(2) and the significant-incident thresholds binding on DNS/cloud/data-centre/MSP/MSSP/trust-service and other digital entities. Use for NIS2 readiness, transposition questions, ENISA technical implementation guidance, significant-incident thresholds, supervisory differences between essential and important entities, and cross-border coordination.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 6 files body ≈ 4 039 tokens Open the sourcegithub.com↗ analyzed 2 h ago

EU NIS2 Directive (Directive (EU) 2022/2555) compliance advisor for essential and important entities: entity classification, Art.

As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, consistency, progress reporting

ProcedureInfrastructureData and analyticsSecuritytype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
96
Quality 40%
85
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Risky intent intent-offensive-security README.md:116
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      We experienced a ransomware attack yesterday that disrupted our online banking services
    • low Risky intent intent-offensive-security references/article-21-measures.md:71
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Apply Secure SDLC practices: threat modelling, code review, SAST/DAST, penetration testing
    • low Risky intent intent-offensive-security SKILL.md:91
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Ransomware example:** encryption of core systems Monday 09:00 → early warning by Tuesday 09:00 (state suspected malicious action = yes); notification by Thursday 09:00 with severity/IoCs; final repo
    • low Risky intent intent-offensive-security SKILL.md:126
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | f | Effectiveness assessment | Audit plan, metrics, pentest/red-team reports | Measures never tested for effectiveness |

    Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 126): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 62/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (nis2) differs from the folder (nis2-tanaji-hemant-naik)
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Result and completion. Output format stated, no completion criterion
    • 70Execution cost. Instruction body is 4039 tokens
    • 85Steps. 23 steps, 2 vague phrases
    • 100Tools and files. No external tools needed
    • 100Running it twice. No mutating operations
    • low 10 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 877: 120–800 characters recommended
    • +4No input/output examples
    • +2Single-language instructions
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 23 items
    • +3Output format is stated explicitly
    • +4Reference files are cited in the instructions (3 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.